High Risk →

mouse_action

Performs non-click mouse actions.

How to control mouse_action ↓

AI agents invoke mouse_action to trigger actions in Tauri Plugin. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

High Risk

This tool simulates mouse input actions (e.g., hover, drag, scroll) on a Tauri application. It triggers external operations by simulating user input, which can interact with UI elements, trigger application logic, and produce side effects depending on the actions performed. Since it's input simulation in a live application, it falls under Execute.

From the tool's definition Performs non-click mouse actions

Documented attack patterns abuse exactly the kind of access mouse_action gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Tauri Plugin, and nothing reaches the server without passing your rules. This is the rule we recommend for mouse_action:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "mouse_action": {
      "limits": [
        {
          "counter": "mouse_action_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

mouse_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Tauri Plugin — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the mouse_action tool do? +

Performs non-click mouse actions. It is categorised as a Execute tool in the Tauri Plugin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mouse_action? +

Register the Tauri Plugin MCP server in PolicyLayer and add a rule for mouse_action: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tauri Plugin. Nothing to install.

What risk level is mouse_action? +

mouse_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mouse_action? +

Yes. Add a rate_limit block to the mouse_action rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block mouse_action completely? +

Set action: deny in the PolicyLayer policy for mouse_action. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides mouse_action? +

mouse_action is provided by the Tauri Plugin MCP server (p3gleg/tauri-plugin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tauri Plugin tool call.

Deterministic rules across all 13 Tauri Plugin tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

13 Tauri Plugin tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.